Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.9829. Min Act: -0.1700
Data Index: 817887 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.9516. Min Act: -0.1700
Data Index: 7788097 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.9516. Min Act: -0.1700
Data Index: 299917 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.9360. Min Act: -0.1700
Data Index: 3013964 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.9203. Min Act: -0.1700
Data Index: 5947021 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.9047. Min Act: -0.1700
Data Index: 5573081 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.9047. Min Act: -0.1700
Data Index: 7563884 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.8578. Min Act: -0.1700
Data Index: 2566124 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.8734. Min Act: -0.1700
Data Index: 4355692 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.8422. Min Act: -0.1700
Data Index: 8766848 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.8109. Min Act: -0.1700
Data Index: 5260113 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.8265. Min Act: -0.1700
Data Index: 5458574 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.8265. Min Act: -0.1700
Data Index: 909527 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.8109. Min Act: -0.1700
Data Index: 3135894 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.8109. Min Act: -0.1700
Data Index: 8441771 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.8109. Min Act: -0.1700
Data Index: 4937556 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.7953. Min Act: -0.1700
Data Index: 460547 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.7953. Min Act: -0.1700
Data Index: 4757186 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.7953. Min Act: -0.1700
Data Index: 5296608 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9829. Min Range: -3.9829
Max Act: 3.7796. Min Act: -0.1700
Data Index: 1809441 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19